Explainability

The field of explainable artificial intelligence (XAI), or interpretable AI, or sometimes explainable Machine Learning is a research field into creating models using the automatic scientific process that allows humans to understand the decisions and predictions made by the model (Gilpin et al. (Explaining explanations: An overview of interpretability of machine learning, IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) pp. 80–89, 2018)). It contrasts with the “black box” concept in machine learning (see Chap. 3 where even its designers cannot explain why a model arrived at a specific decision.